Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1346 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.8167. Min Range: -2.8167

Max Act: 2.8167. Min Act: -0.0000

Data Index: 857580 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 2.8167. Min Range: -2.8167

Max Act: 2.3438. Min Act: -0.0000

Data Index: 262002 (C4 (Web Text))

Max Activating Token Index: 303

Text #2

Max Range: 2.8167. Min Range: -2.8167

Max Act: 2.2597. Min Act: -0.0000

Data Index: 1202040 (C4 (Web Text))

Max Activating Token Index: 581

Text #3

Max Range: 2.8167. Min Range: -2.8167

Max Act: 2.0707. Min Act: -0.0000

Data Index: 778563 (C4 (Web Text))

Max Activating Token Index: 724

Text #4

Max Range: 2.8167. Min Range: -2.8167

Max Act: 2.3119. Min Act: -0.0000

Data Index: 883940 (C4 (Web Text))

Max Activating Token Index: 420

Text #5

Max Range: 2.8167. Min Range: -2.8167

Max Act: 2.2931. Min Act: -0.0000

Data Index: 1096483 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 2.8167. Min Range: -2.8167

Max Act: 2.1395. Min Act: -0.0000

Data Index: 1025867 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 2.8167. Min Range: -2.8167

Max Act: 1.9930. Min Act: -0.0000

Data Index: 819900 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 2.8167. Min Range: -2.8167

Max Act: 1.9586. Min Act: -0.0000

Data Index: 577929 (C4 (Web Text))

Max Activating Token Index: 793

Text #9

Max Range: 2.8167. Min Range: -2.8167

Max Act: 2.0289. Min Act: -0.0000

Data Index: 314759 (C4 (Web Text))

Max Activating Token Index: 399

Text #10

Max Range: 2.8167. Min Range: -2.8167

Max Act: 1.8277. Min Act: -0.0000

Data Index: 680088 (C4 (Web Text))

Max Activating Token Index: 215

Text #11

Max Range: 2.8167. Min Range: -2.8167

Max Act: 1.8966. Min Act: -0.0000

Data Index: 797597 (C4 (Web Text))

Max Activating Token Index: 750

Text #12

Max Range: 2.8167. Min Range: -2.8167

Max Act: 1.7754. Min Act: -0.0000

Data Index: 1179678 (C4 (Web Text))

Max Activating Token Index: 202

Text #13

Max Range: 2.8167. Min Range: -2.8167

Max Act: 1.7660. Min Act: -0.0000

Data Index: 109856 (C4 (Web Text))

Max Activating Token Index: 461

Text #14

Max Range: 2.8167. Min Range: -2.8167

Max Act: 1.8275. Min Act: -0.0000

Data Index: 268572 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 2.8167. Min Range: -2.8167

Max Act: 1.9366. Min Act: -0.0000

Data Index: 40466 (C4 (Web Text))

Max Activating Token Index: 879

Text #16

Max Range: 2.8167. Min Range: -2.8167

Max Act: 1.8103. Min Act: -0.0000

Data Index: 1281784 (C4 (Web Text))

Max Activating Token Index: 907

Text #17

Max Range: 2.8167. Min Range: -2.8167

Max Act: 1.8028. Min Act: 0.0000

Data Index: 18960 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 2.8167. Min Range: -2.8167

Max Act: 1.7085. Min Act: -0.0000

Data Index: 1033181 (C4 (Web Text))

Max Activating Token Index: 587

Text #19

Max Range: 2.8167. Min Range: -2.8167

Max Act: 1.9083. Min Act: -0.0000

Data Index: 1301165 (C4 (Web Text))

Max Activating Token Index: 279